regex-redux Node.js #3 program

// The Computer Language Benchmarks Game
// https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
//
// regex-dna program contributed by Jesse Millikan
// Base on the Ruby version by jose fco. gonzalez
// fixed by Matthew Wilson
// ported to Node.js and sped up by Roman Pletnev
// converted from regex-dna program
// fixed by Josh Goldfoot
// multi thread by Andrey Filatkin

const { Worker, isMainThread, parentPort, workerData } = require('worker_threads');
const fs = require('fs');

if (isMainThread) {
    mainThread();
} else {
    workerThread(workerData);
}

async function mainThread() {
    const regExps = [
        /agggtaaa|tttaccct/ig,
        /[cgt]gggtaaa|tttaccc[acg]/ig,
        /a[act]ggtaaa|tttacc[agt]t/ig,
        /ag[act]gtaaa|tttac[agt]ct/ig,
        /agg[act]taaa|ttta[agt]cct/ig,
        /aggg[acg]aaa|ttt[cgt]ccct/ig,
        /agggt[cgt]aa|tt[acg]accct/ig,
        /agggta[cgt]a|t[acg]taccct/ig,
        /agggtaa[cgt]|[acg]ttaccct/ig
    ];

    let data = fs.readFileSync('/dev/stdin', 'ascii');
    const initialLen = data.length;

    data = data.replace(/^>.*\n|\n/mg, '');
    const cleanedLen = data.length;

    const worker = replaceWork(data);

    for (let j = 0; j < regExps.length; j++) {
        const re = regExps[j];
        const m = data.match(re);
        console.log(re.source, m ? m.length : 0);
    }

    const endLen = await worker;

    console.log(`\n${initialLen}\n${cleanedLen}\n${endLen}`);

    function replaceWork(data) {
        return new Promise(resolve => {
            const worker = new Worker(__filename, {workerData: data});
            worker.on('message', message => {
                resolve(message.data);
            });
        });
    }
}

function workerThread(str) {
    const len = str
        .replace(/tHa[Nt]/g, '<4>')
        .replace(/aND|caN|Ha[DS]|WaS/g, '<3>')
        .replace(/a[NSt]|BY/g, '<2>')
        .replace(/<[^>]*>/g, '|')
        .replace(/\|[^|][^|]*\|/g, '-')
        .length;
    parentPort.postMessage({data: len});
}
    

NOTES:
64-bit Ubuntu quad core
v23.0.0


 Tue, 22 Oct 2024 23:55:32 GMT

MAKE:
cp -L regexredux.node-3.node regexredux.js

0.14s to complete and log all make actions

COMMAND LINE:
 /opt/src/node-v23.0.0/bin/node regexredux.js 0 < regexredux-input5000000.txt

PROGRAM OUTPUT:
agggtaaa|tttaccct 356
[cgt]gggtaaa|tttaccc[acg] 1250
a[act]ggtaaa|tttacc[agt]t 4252
ag[act]gtaaa|tttac[agt]ct 2894
agg[act]taaa|ttta[agt]cct 5435
aggg[acg]aaa|ttt[cgt]ccct 1537
agggt[cgt]aa|tt[acg]accct 1431
agggta[cgt]a|t[acg]taccct 1608
agggtaa[cgt]|[acg]ttaccct 2178

50833411
50000000
27388361